[HN Gopher] Gaussian Frosting: Editable complex radiance fields ...
       ___________________________________________________________________
        
       Gaussian Frosting: Editable complex radiance fields with real-time
       rendering
        
       Author : hellohello2
       Score  : 100 points
       Date   : 2024-09-27 15:10 UTC (1 days ago)
        
 (HTM) web link (anttwo.github.io)
 (TXT) w3m dump (anttwo.github.io)
        
       | peppertree wrote:
       | I can see next paper where you use raytracing for refractive
       | objects, pbr for hard surfaces, and gs for soft surfaces.
        
       | adzm wrote:
       | I can't be the only one who read "edible" in the title.
       | Fascinating work regardless
        
         | eep_social wrote:
         | "frosting" is an extremely strong priming word for "edible" to
         | the point that I suspect this must have been at least a happy
         | accident they left if not completely intentional.
        
         | ajdude wrote:
         | Same here
        
       | vessenes wrote:
       | Paper includes a blender plugin. Very nice. To my non-
       | professional eye, this looks like it works well enough for an
       | indie game dev to give it a try. The method integrates with
       | existing poly-based scenes, so the days of needing a digital hero
       | model built by hand might be over soon. Now can you use a
       | physical model, which is cool and fun.
       | 
       | The general idea here by the way is to take one unconstrained
       | Gaussian pass, hold those gaussians aside, then take another that
       | focuses on densification (they call it regularization), trying to
       | hard constrain the gaussians to the more dense areas of detail.
       | That second set is called the frosting, and it has the nice
       | properties of being smoother; you don't render with it, because
       | it's too smooth. But you do use it to build your meshes. Then
       | they do some magic to key the OG gaussians off the regularized
       | ones, which I didn't understand.
       | 
       | Upshot, this is basically SOTA or close for most Gaussian
       | techniques, definitely SOTA for editable Gaussian techniques in
       | terms of render quality, and also pretty fast -- training a model
       | is something like 90 minutes on a V100. They mentioned in passing
       | in the paper that you can use unconstrained mobile photos, and
       | demo a few, but they didn't talk a lot about the pipeline there.
       | There are just starting to be high quality pipelines that can
       | estimate scene setups without high grade camera information --
       | I'll be curious to look at the code and see what they do there.
        
       ___________________________________________________________________
       (page generated 2024-09-28 23:02 UTC)